Bioelectrical Signals as Emerging Biometrics: Issues and Challenges

Table 2

Performance estimates of various methods using EEG as a biometrics under different validations and test conditions. EO: eye open and EC: eye closed, VEP: visual evoked potential, NN: neural network, MAP: maximum a posteriori model, and HTER: half total error rate defined as (FAR+FRR)/2.

Methods	Data size	Data representation techniques	Classification techniques	Classification accuracy	Test conditions
Poulos et al. [12]	4 subjects 255 EEG epochs	Autoregressive (AR) model	Linear vector quantizer (LVQ) NN	72%–80%	Resting with EO
Paranjape et al. [13]	40 subjects 349 EEG epochs	AR model	Discriminant analysis	80%	Resting with EO, resting with EC
Palaniappan and Mandic [14]	102 subjects 3,560 VEP signals	Multiple signal classification	k-Nearest neighbors (kNN), Elman NN	98.12%±1.26%; 96.13%±1.03%	Eye-blink-free VEP signals
Marcel and Millan [16]	9 subjects	Power spectral density (PSD)	Gaussian mixture model and MAP	N/R HTER: 7.1%–36.0%	Evaluations of hand movements and words generation